Abstract: Systems and methods are disclosed for gradual and/or gradient-based pruning for language-specific multilingual neural machine translation. For example, a method may include determining a pruning mask for weights of a multilingual machine translation model based on a first pruning threshold, wherein the pruning mask includes at least one entry set to zero and at least one entry set to one; training the multilingual machine translation model, while applying the pruning mask to the multilingual machine translation model, for translation between a language pair based on training examples from a bilingual translation corpus; updating the pruning mask based on a second pruning threshold; and training the multilingual machine translation model, while applying the updated pruning mask to the multilingual machine translation model, for translation between the language pair based on training examples from the bilingual translation corpus. For example, the weights may be pruned based on gradient-based scores.

Abstract: An example method includes hosting, by a conference provider, a virtual conference between a plurality of client devices exchanging audio streams; translating, by a translation process, a first transcription of a first audio stream in a first language to create a first translation, translating, by the translation process, a second transcription of a second audio stream in a second language different than the first language to create a second translation; and providing, during the virtual conference, the first translation and the second translation to a first client device and a second client device of the plurality of client devices.

Abstract: An example method includes executing a plurality of transcription and translation processes, each executed transcription and translation process associated with one of a plurality of input languages, each translation process associated with one of a plurality of output languages; hosting a plurality of virtual conferences, each virtual conference between a plurality of client devices exchanging audio streams; receiving, during one or more of the virtual conferences, requests from client devices to translate audio streams within the respective conferences; allocating, during the respective conferences and in response to the respective requests to translate, one or more transcription processes and one or more translation processes to the respective virtual conferences based on a source language being used in the respective virtual conference; providing, during the respective virtual conferences, one or more audio streams from the respective virtual conferences to the respective allocated transcription process;

Abstract: Aspects of the invention include methods of generating models for scoring patient notes. The methods include receiving a sample of patient notes, extracting a plurality of ngrams from the sample of patient notes, clustering the plurality of extracted ngrams that meet a similarity threshold into a plurality of lists, identifying a feature associated with each of the plurality of lists based on the ngrams in that list and designating at least one ngram in each list as evidence of the feature associated with that list. The identified features and designated ngram are stored in models for scoring patient notes.